In this paper, we show that such NP-hard projections can not only be avoided by appealing to submodular optimization, but such methods come with strong theoretical guarantees even in the presence of poorly conditioned data (i.e. say when two features have

A new method for learning variational autoencoders (V AEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the encoder distribution. Performance is further enhanced by integrating the proposed encoder with importance sampling. Excellent performance is demonstrated across multiple unsupervised and semi-supervised problems, including semi-supervised analysis of the ImageNet data, demonstrating the scalability of the model to large datasets.

Neural Information Processing Systems http://nips.cc/

Conditional probabilities are a core concept in machine learning.

These solutions provide detailed information about the performance of the ICA algorithm, as many practical performance metrics are functionals of the joint empirical measures.

In this paper, we study the mixed linear regression (MLR) problem, where the goal is to recover multiple underlying linear models from their unlabeled linear measurements.

In addition to the principle of LKIS, an implementation using neural networks is described.

We illustrate the method's performances in comparison

Exponential number of classes: this brings both additional computational and statistical challenges. By exponential, we mean exponentially large in the size of the natural dimension of output, e.g., the

Neural Information Processing Systems http://nips.cc/